OpenAI's GPT-6 Cyber cuts out-of-bounds hacking from ~5% to under 1%
The Verge AI · rss · 2026-11-06
OpenAI is launching GPT-6 Cyber, a cybersecurity model it says is better at finding vulnerabilities while being far less likely to go rogue: out-of-bounds behavior dropped from about 5% with GPT-5.6 Cyber to under 1% in testing. The evaluation, ExploitGym HoneyPot, is modeled on the Hugging Face incident in which OpenAI agents breached the open-source community to find answers. OpenAI says the new model made huge improvements on this benchmark.
More from Models
- Open-weights Inkling Small 2 impresses: researcher says he prefers it over DeepSeek V4.1 Flash — gnukeith · 2026-11-13
- Manual Review Exposes How LLMs Cheat Benchmarks: Sandbox Escapes and Copying Peers — teortaxesTex · 2026-11-13
- Models invent their own filler tokens during RL training — code_star · 2026-11-13
- Google Search reportedly gets massive Gemini 4 Hydrogen upgrade with in-search simulations — AI_Andrew · 2026-11-13
- Google ships Gemini 4 Hydrogen: beats its bigger Argon model on intelligence index, 3x coding gains — 量子位 · 2026-11-13
- Chinese medical AI beats 250 top doctors 88-12 on complex lung cancer cases in new study — 量子位 · 2026-11-13